Whole Genome Sequencing and a New Bioinformatics Platform Allow for Rapid Gene Identification in D. melanogaster EMS Screens

Abstract

Forward genetic screens in Drosophila melanogaster using ethyl methanesulfonate (EMS) mutagenesis are a powerful approach for identifying genes that modulate specific biological processes in an in vivo setting. The mapping of genes that contain randomly-induced point mutations has become more efficient in Drosophila thanks to the maturation and availability of many types of genetic tools. However, classic approaches to gene mapping are relatively slow and ultimately require extensive Sanger sequencing of candidate chromosomal loci. With the advent of new high-throughput sequencing techniques, it is increasingly efficient to directly re-sequence the whole genome of model organisms. This approach, in combination with traditional chromosomal mapping, has the potential to greatly simplify and accelerate mutation identification in mutants generated in EMS screens. Here we show that next-generation sequencing (NGS) is an accurate and efficient tool for high-throughput sequencing and mutation discovery in Drosophila melanogaster. As a test case, mutant strains of Drosophila that exhibited long-term survival of severed peripheral axons were identified in a forward EMS mutagenesis. All mutants were recessive and fell into a single lethal complementation group, which suggested that a single gene was responsible for the protective axon degenerative phenotype. Whole genome sequencing of these genomes identified the underlying gene ect4. To improve the process of genome wide mutation identification, we developed Genomes Management Application (GEM.app, https://genomics.med.miami.edu), a graphical online user interface to a custom query framework. Using a custom GEM.app query, we were able to identify that each mutant carried a unique non-sense mutation in the gene ect4 (dSarm), which was recently shown by Osterloh et al. to be essential for the activation of axonal degeneration. Our results demonstrate the current advantages and limitations of NGS in Drosophila and we introduce GEM.app as a simple yet powerful genomics analysis tool for the Drosophila community. At a current cost of <$1,000 per genome, NGS should thus become a standard gene discovery tool in EMS induced genetic forward screens.

Figure 1

Distribution of detected SNVs not present in background on each chromosome.Purple bars represent the total number of SNVs that were observed in mutant genomes but not in the background genome. Green bars represent the number of SNVs that were G>A or C>T transitions. Red bars represent the number of nonsynonymous or splice-site SNVs that were not present in the wild-type genome and detected in the mutant genomes. Blue bars represent the number of nonsynonymous and splice-site SNVs that were G>A or C>T transitions.

Figure 2

Filtering strategies used for gene identification by whole genome sequencing. Each box lists the number of genes with one or more protein-coding SNV (cSNV). Columns show the effect of requiring that one or more cSNV be observed in each of one to three mutant flies. Rows show the effect of filtering variants that meet certain analysis criteria. Row 6 displays the effect of including 8 samples from different screens in analysis.

Figure 3

Mutation density on chromosome 3L in screen (N = 3). (A) Screenshot of chromosome 3L with custom tracks in the UCSC genome browser. The pink line displays all SNVs on chromosome 3L that were detected in this screen. The navy line displays all heterozygous non-synonymous and splice-site SNVs on chromosome 3L not present in the wild-type fly. (B) Screen shot of ect4/dSarm with custom track displaying the location and conservation of the three ect4 mutations.

Figure 4

GEM.app bioinformatics pipeline and online graphical interface. (A) The systematic processes of the automated GEM.app bioinformatics pipeline. (B) Screenshot of the GEM.app form with some of the filtering options displayed. (C) The output of GEM.app query used to identify ect4 mutations. A subset of 34 total columns are shown. Links within the table (U, N, S, e) provide direct access to common resources, such as UCSC genome browser, NCBI, String gene networks, and Ensembl. Up to three tabs allow for parallel queries. Additional options include modifying filter settings, managing columns, and downloading results in an excel sheet.